A self-hosted alternative to DocuWare that automates document organization using local AI. Integrates Tesseract OCR and LLMs to extract metadata, tag files, and enable semantic search across scanned PDFs.
Tech Stack
PythonFile Mgmt & Sharing
Why Custodian?
• Automated metadata extraction
• Semantic search capabilities
• Self-hosted privacy
Limitations
• High RAM usage for AI models
• Complex initial configuration
• OCR speed depends on hardware
10/22/2025
Last Update
0
Forks
0
Issues
MIT
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to Custodian instantly boosts your runway.
